Dataset Information

Structure-revealing data fusion.

ABSTRACT:

Background

Analysis of data from multiple sources has the potential to enhance knowledge discovery by capturing underlying structures, which are, otherwise, difficult to extract. Fusing data from multiple sources has already proved useful in many applications in social network analysis, signal processing and bioinformatics. However, data fusion is challenging since data from multiple sources are often (i) heterogeneous (i.e., in the form of higher-order tensors and matrices), (ii) incomplete, and (iii) have both shared and unshared components. In order to address these challenges, in this paper, we introduce a novel unsupervised data fusion model based on joint factorization of matrices and higher-order tensors.

Results

While the traditional formulation of coupled matrix and tensor factorizations modeling only shared factors fails to capture the underlying structures in the presence of both shared and unshared factors, the proposed data fusion model has the potential to automatically reveal shared and unshared components through modeling constraints. Using numerical experiments, we demonstrate the effectiveness of the proposed approach in terms of identifying shared and unshared components. Furthermore, we measure a set of mixtures with known chemical composition using both LC-MS (Liquid Chromatography - Mass Spectrometry) and NMR (Nuclear Magnetic Resonance) and demonstrate that the structure-revealing data fusion model can (i) successfully capture the chemicals in the mixtures and extract the relative concentrations of the chemicals accurately, (ii) provide promising results in terms of identifying shared and unshared chemicals, and (iii) reveal the relevant patterns in LC-MS by coupling with the diffusion NMR data.

Conclusions

We have proposed a structure-revealing data fusion model that can jointly analyze heterogeneous, incomplete data sets with shared and unshared components and demonstrated its promising performance as well as potential limitations on both simulated and real data.

SUBMITTER: Acar E

PROVIDER: S-EPMC4117975 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Fusing complementary information from different modalities can lead to the discovery of more accurate diagnostic biomarkers for psychiatric disorders. However, biomarker discovery through data fusion is challenging since it requires extracting interpretable and reproducible patterns from data sets, consisting of shared/unshared patterns and of different orders. For example, multi-channel electroencephalography (EEG) signals from multiple subjects can be represented as a third-order tensor with modes: subject, time, and channel, while functional magnetic resonance imaging (fMRI) data may be in the form of subject by voxel matrices. Traditional data fusion methods rearrange higher-order tensors, such as EEG, as matrices to use matrix factorization-based approaches. In contrast, fusion methods based on coupled matrix and tensor factorizations (CMTF) exploit the potential multi-way structure of higher-order tensors. The CMTF approach has been shown to capture underlying patterns more accurately without imposing strong constraints on the latent neural patterns, i.e., biomarkers. In this paper, EEG, fMRI, and structural MRI (sMRI) data collected during an auditory oddball task (AOD) from a group of subjects consisting of patients with schizophrenia and healthy controls, are arranged as matrices and higher-order tensors coupled along the subject mode, and jointly analyzed using structure-revealing CMTF methods [also known as advanced CMTF (ACMTF)] focusing on unique identification of underlying patterns in the presence of shared/unshared patterns. We demonstrate that joint analysis of the EEG tensor and fMRI matrix using ACMTF reveals significant and biologically meaningful components in terms of differentiating between patients with schizophrenia and healthy controls while also providing spatial patterns with high resolution and improving the clustering performance compared to the analysis of only the EEG tensor. We also show that these patterns are reproducible, and study reproducibility for different model parameters. In comparison to the joint independent component analysis (jICA) data fusion approach, ACMTF provides easier interpretation of EEG data by revealing a single summary map of the topography for each component. Furthermore, fusion of sMRI data with EEG and fMRI through an ACMTF model provides structural patterns; however, we also show that when fusing data sets from multiple modalities, hence of very different nature, preprocessing plays a crucial role.

Project description:Butyrate-producing bacteria have recently gained attention, since they are important for a healthy colon and when altered contribute to emerging diseases, such as ulcerative colitis and type II diabetes. This guild is polyphyletic and cannot be accurately detected by 16S rRNA gene sequencing. Consequently, approaches targeting the terminal genes of the main butyrate-producing pathway have been developed. However, since additional pathways exist and alternative, newly recognized enzymes catalyzing the terminal reaction have been described, previous investigations are often incomplete. We undertook a broad analysis of butyrate-producing pathways and individual genes by screening 3,184 sequenced bacterial genomes from the Integrated Microbial Genome database. Genomes of 225 bacteria with a potential to produce butyrate were identified, including many previously unknown candidates. The majority of candidates belong to distinct families within the Firmicutes, but members of nine other phyla, especially from Actinobacteria, Bacteroidetes, Fusobacteria, Proteobacteria, Spirochaetes, and Thermotogae, were also identified as potential butyrate producers. The established gene catalogue (3,055 entries) was used to screen for butyrate synthesis pathways in 15 metagenomes derived from stool samples of healthy individuals provided by the HMP (Human Microbiome Project) consortium. A high percentage of total genomes exhibited a butyrate-producing pathway (mean, 19.1%; range, 3.2% to 39.4%), where the acetyl-coenzyme A (CoA) pathway was the most prevalent (mean, 79.7% of all pathways), followed by the lysine pathway (mean, 11.2%). Diversity analysis for the acetyl-CoA pathway showed that the same few firmicute groups associated with several Lachnospiraceae and Ruminococcaceae were dominating in most individuals, whereas the other pathways were associated primarily with Bacteroidetes. IMPORTANCE Microbiome research has revealed new, important roles of our gut microbiota for maintaining health, but an understanding of effects of specific microbial functions on the host is in its infancy, partly because in-depth functional microbial analyses are rare and publicly available databases are often incomplete/misannotated. In this study, we focused on production of butyrate, the main energy source for colonocytes, which plays a critical role in health and disease. We have provided a complete database of genes from major known butyrate-producing pathways, using in-depth genomic analysis of publicly available genomes, filling an important gap to accurately assess the butyrate-producing potential of complex microbial communities from "-omics"-derived data. Furthermore, a reference data set containing the abundance and diversity of butyrate synthesis pathways from the healthy gut microbiota was established through a metagenomics-based assessment. This study will help in understanding the role of butyrate producers in health and disease and may assist the development of treatments for functional dysbiosis.